⚡️ Speed up function normalize_string_prefix by 9% in src/black/strings.py

[codeflash-ai]

📄 normalize_string_prefix in src/black/strings.py

✨ Performance Summary:

• Speed Increase: 📈 9% (0.09x faster)
• Runtime Reduction: ⏱️ From 318 microseconds down to 291 microseconds (best of 340 runs)

---

📝 Explanation and details

To optimize the provided Python program, we can avoid the regular expression matching and use direct string operations which are generally faster for this use case. Here’s an optimized version of the program.

---

✅ Correctness verification

The new optimized code was tested for correctness. The results are listed below:

Test	Status	Details
⚙️ Existing Unit Tests	🔘 None Found
🌀 Generated Regression Tests	✅ 59 Passed	See below
⏪ Replay Tests	🔘 None Found
🔎 Concolic Coverage Tests	✅ 1 Passed
📊 Coverage	100.0%

🌀 Generated Regression Tests Details

Click to view details

import re
from typing import Final

# imports
import pytest  # used for our unit tests
from black.strings import normalize_string_prefix

# function to test
STRING_PREFIX_CHARS = "FfBbUuRr"

STRING_PREFIX_RE: Final = re.compile(
    r"^([" + STRING_PREFIX_CHARS + r"]*)(.*)$", re.DOTALL
)
from black.strings import normalize_string_prefix


# unit tests
def test_basic_prefix_normalization():
    codeflash_output = normalize_string_prefix("F")
    codeflash_output = normalize_string_prefix("B")
    codeflash_output = normalize_string_prefix("UF")
    codeflash_output = normalize_string_prefix("uB")

def test_strings_without_prefixes():
    codeflash_output = normalize_string_prefix("hello")
    codeflash_output = normalize_string_prefix("world")
    codeflash_output = normalize_string_prefix("")

def test_mixed_case_prefixes():
    codeflash_output = normalize_string_prefix("fB")
    codeflash_output = normalize_string_prefix("Fb")
    codeflash_output = normalize_string_prefix("uF")
    codeflash_output = normalize_string_prefix("Ub")

def test_prefixes_with_r():
    codeflash_output = normalize_string_prefix("r")
    codeflash_output = normalize_string_prefix("Fr")
    codeflash_output = normalize_string_prefix("Br")
    codeflash_output = normalize_string_prefix("Ur")
    codeflash_output = normalize_string_prefix("uR")
    codeflash_output = normalize_string_prefix("rf")
    codeflash_output = normalize_string_prefix("rb")

def test_no_prefix_characters():
    codeflash_output = normalize_string_prefix("12345")
    codeflash_output = normalize_string_prefix("!@#$%")

def test_multiple_prefix_characters():
    codeflash_output = normalize_string_prefix("FU")
    codeflash_output = normalize_string_prefix("UB")
    codeflash_output = normalize_string_prefix("UFr")
    codeflash_output = normalize_string_prefix("uBr")

def test_edge_cases():
    codeflash_output = normalize_string_prefix("rF")
    codeflash_output = normalize_string_prefix("rB")
    codeflash_output = normalize_string_prefix("rU")
    codeflash_output = normalize_string_prefix("ru")
    codeflash_output = normalize_string_prefix("rFU")
    codeflash_output = normalize_string_prefix("rUB")

def test_large_scale():
    codeflash_output = normalize_string_prefix("F" + "a" * 10000)
    codeflash_output = normalize_string_prefix("a" * 10000)


def test_strings_with_newlines():
    codeflash_output = normalize_string_prefix("Fhello\nworld")
    codeflash_output = normalize_string_prefix("Bhello\nworld")

def test_strings_with_special_characters():
    codeflash_output = normalize_string_prefix("F!@#$%^&*()")
    codeflash_output = normalize_string_prefix("B12345")

def test_strings_with_escape_characters():
    codeflash_output = normalize_string_prefix("F\thello")
    codeflash_output = normalize_string_prefix("B\nworld")

def test_strings_with_mixed_content():
    codeflash_output = normalize_string_prefix("Fabc123!@#")
    codeflash_output = normalize_string_prefix("Bxyz789$%^")
# codeflash_output is used to check that the output of the original code is the same as that of the optimized code.
import re
from typing import Final

# imports
import pytest  # used for our unit tests
from black.strings import normalize_string_prefix

# function to test
STRING_PREFIX_CHARS = "fFrRbBuU"

STRING_PREFIX_RE: Final = re.compile(
    r"^([" + STRING_PREFIX_CHARS + r"]*)(.*)$", re.DOTALL
)
from black.strings import normalize_string_prefix

# unit tests

def test_basic_prefix_normalization():
    # Single prefix normalization
    codeflash_output = normalize_string_prefix("F'hello'")
    codeflash_output = normalize_string_prefix("B'hello'")

def test_multiple_prefixes():
    # Multiple prefixes normalization and ordering
    codeflash_output = normalize_string_prefix("Fr'hello'")
    codeflash_output = normalize_string_prefix("RF'hello'")
    codeflash_output = normalize_string_prefix("uR'hello'")
    codeflash_output = normalize_string_prefix("Ur'hello'")

def test_prefix_removal():
    # Prefix removal
    codeflash_output = normalize_string_prefix("u'hello'")
    codeflash_output = normalize_string_prefix("U'hello'")

def test_mixed_case_prefixes():
    # Mixed case prefixes normalization
    codeflash_output = normalize_string_prefix("Fr'hello'")
    codeflash_output = normalize_string_prefix("fR'hello'")

def test_no_prefix():
    # No prefix
    codeflash_output = normalize_string_prefix("'hello'")
    codeflash_output = normalize_string_prefix('"hello"')


def test_empty_string():
    # Empty string
    codeflash_output = normalize_string_prefix("")

def test_strings_with_newlines():
    # Strings containing newlines
    codeflash_output = normalize_string_prefix("F'hello\nworld'")
    codeflash_output = normalize_string_prefix("r'hello\nworld'")

def test_strings_with_special_characters():
    # Strings containing special characters
    codeflash_output = normalize_string_prefix("F'hello\\nworld'")
    codeflash_output = normalize_string_prefix("r'hello\\tworld'")

def test_large_scale():
    # Large scale test cases to assess performance and scalability
    large_string = "a" * 1000000
    codeflash_output = normalize_string_prefix(f"F'{large_string}'")
    codeflash_output = normalize_string_prefix(f"u'{large_string}'")
# codeflash_output is used to check that the output of the original code is the same as that of the optimized code.

---

📣 **Feedback**

If you have any feedback or need assistance, feel free to join our Discord community: